{"id":"https://openalex.org/W4403871010","doi":"https://doi.org/10.1063/5.0238090","title":"PhysBERT: A text embedding model for physics scientific literature","display_name":"PhysBERT: A text embedding model for physics scientific literature","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4403871010","doi":"https://doi.org/10.1063/5.0238090"},"language":"en","primary_location":{"id":"doi:10.1063/5.0238090","doi":"https://doi.org/10.1063/5.0238090","is_oa":true,"landing_page_url":"https://doi.org/10.1063/5.0238090","pdf_url":"https://pubs.aip.org/aip/aml/article-pdf/doi/10.1063/5.0238090/20227307/046105_1_5.0238090.pdf","source":{"id":"https://openalex.org/S4387287287","display_name":"APL Machine Learning","issn_l":"2770-9019","issn":["2770-9019"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1"],"host_organization":"https://openalex.org/P4310320257","host_organization_name":"American Institute of Physics","host_organization_lineage":["https://openalex.org/P4310320257"],"host_organization_lineage_names":["American Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APL Machine Learning","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://pubs.aip.org/aip/aml/article-pdf/doi/10.1063/5.0238090/20227307/046105_1_5.0238090.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089272150","display_name":"Thorsten Hellert","orcid":"https://orcid.org/0000-0002-2797-0926","observed_orcids":["https://orcid.org/0000-0002-2797-0926"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thorsten Hellert","raw_affiliation_strings":["Lawrence Berkeley National Laboratory 1 , Berkeley, California 94720,","Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA"],"raw_orcid":"https://orcid.org/0000-0002-2797-0926","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory 1 , Berkeley, California 94720,","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jo\u00e3o Montenegro","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Montenegro","raw_affiliation_strings":["Lawrence Berkeley National Laboratory 1 , Berkeley, California 94720,","Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory 1 , Berkeley, California 94720,","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089644865","display_name":"Andrea Pollastro","orcid":"https://orcid.org/0000-0003-4075-0757","observed_orcids":["https://orcid.org/0000-0003-4075-0757"]},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Pollastro","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II 2 , 80125 Naples,","Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4075-0757","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II 2 , 80125 Naples,","institution_ids":["https://openalex.org/I71267560"]},{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, 80125 Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089272150"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.4853,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63790955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain-specific-language-models","display_name":"domain-specific language models","score":0.6309999823570251},{"id":"https://openalex.org/keywords/physics-literature","display_name":"physics literature","score":0.6150000095367432},{"id":"https://openalex.org/keywords/arxiv-papers","display_name":"arXiv papers","score":0.8450000286102295},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.382999986410141},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.6800000071525574},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.6700000166893005}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5904699563980103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3944501280784607},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.37489575147628784},{"id":"https://openalex.org/C33332235","wikidata":"https://www.wikidata.org/wiki/Q18362","display_name":"Theoretical physics","level":1,"score":0.33296287059783936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16904199123382568}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1063/5.0238090","doi":"https://doi.org/10.1063/5.0238090","is_oa":true,"landing_page_url":"https://doi.org/10.1063/5.0238090","pdf_url":"https://pubs.aip.org/aip/aml/article-pdf/doi/10.1063/5.0238090/20227307/046105_1_5.0238090.pdf","source":{"id":"https://openalex.org/S4387287287","display_name":"APL Machine Learning","issn_l":"2770-9019","issn":["2770-9019"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1"],"host_organization":"https://openalex.org/P4310320257","host_organization_name":"American Institute of Physics","host_organization_lineage":["https://openalex.org/P4310320257"],"host_organization_lineage_names":["American Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APL Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4b7c96143fb34bfaac0a949fd4d15dc4","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/4b7c96143fb34bfaac0a949fd4d15dc4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"APL Machine Learning, Vol 2, Iss 4, Pp 046105-046105-8 (2024)","raw_type":"article"},{"id":"pmh:oai:osti.gov:2564799","doi":null,"is_oa":false,"landing_page_url":"https://www.osti.gov/biblio/2564799","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1063/5.0238090","doi":"https://doi.org/10.1063/5.0238090","is_oa":true,"landing_page_url":"https://doi.org/10.1063/5.0238090","pdf_url":"https://pubs.aip.org/aip/aml/article-pdf/doi/10.1063/5.0238090/20227307/046105_1_5.0238090.pdf","source":{"id":"https://openalex.org/S4387287287","display_name":"APL Machine Learning","issn_l":"2770-9019","issn":["2770-9019"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1"],"host_organization":"https://openalex.org/P4310320257","host_organization_name":"American Institute of Physics","host_organization_lineage":["https://openalex.org/P4310320257"],"host_organization_lineage_names":["American Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APL Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G122673668","display_name":null,"funder_award_id":"DE\u2013AC02\u201305CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G1677143136","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G419881185","display_name":null,"funder_award_id":"DEAC02\u201305CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G42916606","display_name":null,"funder_award_id":"DE AC02 05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7309032566","display_name":null,"funder_award_id":"ERCAP0027412","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403871010.pdf","grobid_xml":"https://content.openalex.org/works/W4403871010.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W8870360","https://openalex.org/W1614298861","https://openalex.org/W2101234009","https://openalex.org/W2131676173","https://openalex.org/W2138615112","https://openalex.org/W2787560479","https://openalex.org/W2798812533","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2919115771","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W2970771982","https://openalex.org/W2979826702","https://openalex.org/W3027879771","https://openalex.org/W3086105743","https://openalex.org/W3149778443","https://openalex.org/W3153833878","https://openalex.org/W3156636935","https://openalex.org/W3185250692","https://openalex.org/W3201869313","https://openalex.org/W4221142221","https://openalex.org/W4309674289","https://openalex.org/W4310923309","https://openalex.org/W4322766882","https://openalex.org/W4382246105","https://openalex.org/W4384388099","https://openalex.org/W4386228584","https://openalex.org/W4386576685","https://openalex.org/W4387687508","https://openalex.org/W4388093226","https://openalex.org/W4388978389","https://openalex.org/W4389331093","https://openalex.org/W4389524502","https://openalex.org/W4389984066","https://openalex.org/W4399912019","https://openalex.org/W4400531953","https://openalex.org/W4402671936","https://openalex.org/W4409216061","https://openalex.org/W4409657302","https://openalex.org/W4411119057"],"related_works":["https://openalex.org/W7104246999","https://openalex.org/W4409429506","https://openalex.org/W4399159326","https://openalex.org/W2973154071","https://openalex.org/W2922551710","https://openalex.org/W7207867964","https://openalex.org/W4404987491","https://openalex.org/W6958878575","https://openalex.org/W7164779588","https://openalex.org/W7090717199"],"abstract_inverted_index":{"The":[0],"specialized":[1],"language":[2],"and":[3,40,67],"complex":[4],"concepts":[5],"in":[6,83],"physics":[7,65,87],"pose":[8],"significant":[9],"challenges":[10],"for":[11,36,85],"information":[12,38],"extraction":[13],"through":[14],"Natural":[15],"Language":[16],"Processing":[17],"(NLP).":[18],"Central":[19],"to":[20],"effective":[21],"NLP":[22],"applications":[23],"is":[24],"the":[25,49,81],"text":[26,31,52],"embedding":[27,53],"model,":[28],"which":[29],"converts":[30],"into":[32],"dense":[33],"vector":[34],"representations":[35],"efficient":[37],"retrieval":[39],"semantic":[41],"analysis.":[42],"In":[43],"this":[44],"work,":[45],"we":[46],"introduce":[47],"PhysBERT,":[48],"first":[50],"physics-specific":[51,78],"model.":[54],"Pre-trained":[55],"on":[56,77],"a":[57],"curated":[58],"corpus":[59],"of":[60],"1.2":[61],"\u00d7":[62],"106":[63],"arXiv":[64],"papers":[66],"fine-tuned":[68],"with":[69],"supervised":[70],"data,":[71],"PhysBERT":[72],"outperforms":[73],"leading":[74],"general-purpose":[75],"models":[76],"tasks,":[79],"including":[80],"effectiveness":[82],"fine-tuning":[84],"specific":[86],"subdomains.":[88]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-10-30T00:00:00"}